Multi-thread low-power-consumption intelligent monitoring system based on AI processor

By combining the RK3588 processor with a multi-core CPU architecture, multi-threaded task scheduling, and model quantization, a balance between low power consumption and high computing power is achieved in the intelligent monitoring system. This solves the problems of low resource utilization and long latency in existing technologies, and improves the system's computing efficiency and scalability.

CN121708449APending Publication Date: 2026-03-20FOCALCREST LTD
0 Cites 5 Cited by

Patent Information

Application Number
CN202511504664.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-21
Publication Date
2026-03-20

AI Technical Summary

Technical Problem

Existing intelligent monitoring systems suffer from imbalances in computing power and power consumption, rigid hardware dependencies, and insufficient edge-side optimization, making it difficult to balance high-concurrency analysis with low-power operation. They also have low resource utilization and long latency.

Method used

The system adopts the RK3588 processor, which integrates an NPU module and a multi-core CPU architecture. It combines a multi-threaded task scheduling module, a model quantization module, a batch processing optimization unit, a zero-copy video stream processing architecture, an energy efficiency control module, a multi-model collaborative inference engine, and a frame ID synchronization unit. Through dynamic thread pool management, INT8 quantization, heterogeneous batch processing, zero-copy video stream processing, and a distributed inference coordinator, it achieves coordinated optimization of low power consumption and high computing power.

Benefits of technology

In a scenario with 8 concurrent video streams, power consumption was reduced to 8.2W, computing power was stabilized at 6.8TOPS, MAC unit utilization was increased to 92%, end-to-end latency was compressed to 180ms, spatiotemporal alignment accuracy was 99.7%, resource reuse rate was increased by 40%, scalability was increased by 3 times, throughput was increased to 220FPS, and data copying time was reduced by 90%.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent monitoring, in particular to a multi-thread low-power-consumption intelligent monitoring system based on an AI processor. The method has the advantages that aiming at the problems of unbalanced computing power and power consumption, high multi-task processing delay and strong hardware dependence in the prior art, the NPU module of the RK3588 processor is combined with the INT8 quantitative model, so that the power consumption is lower than 10W under the 6TOPS computing power; a dynamic multi-thread scheduling mechanism is designed, parallel processing of more than eight paths of video streams is supported through binding of a priority queue and an NPU core, and end-to-end delay is compressed to be within 200 ms; a zero-copy video stream architecture is constructed, data transfer is eliminated through memory mapping, and preprocessing time consumption is reduced by 90%; an energy efficiency control module is integrated, the NPU voltage frequency is dynamically adjusted according to the load, and the energy efficiency ratio reaches 0.83 TOPS / W; space-time alignment of multi-model reasoning results is realized by adopting a frame ID synchronization technology, and the mismatching rate is lower than 0.1%.
Need to check novelty before this filing date? Find Prior Art